Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Tone down visual noise — lowers variance and motion, simplifies layout and color weight, keeps hierarchy clear. Use when the UI feels loud, busy, or over-designed, or when the user says "quieter", "more restrained", "simpler", or "tone it down". Invoke when the user asks for quieter on their UI, or mentions 'quieter' alongside design / UI / frontend work.
.claude/skills/educlopez-quieter/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✓→✗ | ▼ Worse | -83% | 0% |
| case-02 | ✓→✗ | ▼ Worse | -87% | 0% |
| case-04 | ✓→✗ | ▼ Worse | -83% | 0% |
| case-05 | ✓→✗ | ▼ Worse | -54% | 0% |
| case-06 | ✓→✗ | ▼ Worse | 32% | 0% |
<!-- HARNESS MIRROR — do not edit here. Canonical source: commands/quieter.md. After editing source, copy into cli/assets/<harness>/ and repo-root harness mirrors. -->
Context: this sub-skill is one lens of the broader ui-craft skill. If the ui-craft skill is also installed, read its SKILL.md first for Discovery + Anti-Slop + Craft Test, then apply the specific lens below.
Make the UI at $ARGUMENTS quieter. Load the ui-craft skill and read references/craft-intent.md.
Reduce amplitude without gutting hierarchy. Calm ≠ boring.
Apply in order (edit code directly):
Preserve: primary hierarchy, one CTA level, accessibility, states, signature detail only if it carries meaning (else simplify it).
Overlap: for structural cuts (sections, copy), also apply /distill logic. For color strategy, see /colorize.
Output: edit code. Print Review Format table. End with the updated Craft Read line.
Next step: /critique — confirm restraint did not flatten the hierarchy (rung 1).
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→fail | 21,203 | 8,573 | -60% | 1 | 1 | 0% | 3,797 | 628 | -83% | 0 | 0 | — |
case-02 | pass→fail | 25,634 | 3,579 | -86% | 1 | 1 | 0% | 4,612 | 589 | -87% | 0 | 0 | — |
case-03 | fail→fail | 14,777 | 3,736 | -75% | 1 | 1 | 0% | 3,079 | 588 | -81% | 0 | 0 | — |
case-09 | pass→pass | 11,490 | 10,856 | -6% | 1 | 1 | 0% | 2,245 | 2,497 | +11% | 0 | 0 | — |
case-04 | pass→fail | 25,000 | 6,553 | -74% | 1 | 1 | 0% | 5,766 | 1,002 | -83% | 0 | 0 | — |
case-05 | pass→fail | 8,745 | 5,147 | -41% | 1 | 1 | 0% | 1,838 | 847 | -54% | 0 | 0 | — |
case-06 | pass→fail | 21,869 | 26,827 | +23% | 1 | 1 | 0% | 4,987 | 6,602 | +32% | 0 | 0 | — |
case-07 | fail→fail | 5,026 | 4,411 | -12% | 1 | 1 | 0% | 283 | 637 | +125% | 0 | 0 | — |
case-08 | fail→fail | 5,016 | 4,166 | -17% | 1 | 1 | 0% | 320 | 763 | +138% | 0 | 0 | — |
case-10 | fail→fail | 13,687 | 4,650 | -66% | 1 | 1 | 0% | 2,512 | 863 | -66% | 0 | 0 | — |
case-11 | pass→fail | 9,457 | 4,245 | -55% | 1 | 1 | 0% | 1,849 | 743 | -60% | 0 | 0 | — |
case-12 | fail→fail | 3,942 | 4,034 | +2% | 1 | 1 | 0% | 199 | 597 | +200% | 0 | 0 | — |
case-13 | fail→fail | 3,889 | 4,386 | +13% | 1 | 1 | 0% | 222 | 556 | +150% | 0 | 0 | — |
case-14 | fail→fail | 7,839 | 1,612 | -79% | 1 | 1 | 0% | 1,171 | 714 | -39% | 0 | 0 | — |
case-15 | fail→fail | 7,090 | 2,192 | -69% | 1 | 1 | 0% | 1,177 | 814 | -31% | 0 | 0 | — |
case-16 | fail→fail | 5,642 | 1,421 | -75% | 1 | 1 | 0% | 923 | 642 | -30% | 0 | 0 | — |
case-17 | pass→pass | 9,070 | 10,461 | +15% | 1 | 1 | 0% | 1,563 | 2,482 | +59% | 0 | 0 | — |
case-18 | fail→fail | 5,651 | 1,579 | -72% | 1 | 1 | 0% | 901 | 650 | -28% | 0 | 0 | — |
case-23 | pass→fail | 22,464 | 4,332 | -81% | 1 | 1 | 0% | 5,190 | 726 | -86% | 0 | 0 | — |
case-19 | pass→fail | 17,097 | 3,687 | -78% | 1 | 1 | 0% | 3,484 | 559 | -84% | 0 | 0 | — |
case-20 | fail→fail | 4,874 | 3,980 | -18% | 1 | 1 | 0% | 422 | 590 | +40% | 0 | 0 | — |
case-21 | fail→fail | 13,014 | 2,231 | -83% | 1 | 1 | 0% | 1,110 | 830 | -25% | 0 | 0 | — |
case-22 | fail→fail | 3,883 | 5,382 | +39% | 1 | 1 | 0% | 230 | 761 | +231% | 0 | 0 | — |
case-24 | fail→fail | 8,096 | 2,505 | -69% | 1 | 1 | 0% | 1,588 | 949 | -40% | 0 | 0 | — |
case-25 | pass→pass | 12,388 | 8,373 | -32% | 1 | 1 | 0% | 2,134 | 1,948 | -9% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 25 cases were attempted, and 11 counted toward the lift figure. The other 14 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of -32 percentage points is the difference between those two pass rates over the 11 comparable cases. 11 cases got worse with the skill loaded, and they are included in that figure.
Other measured skills in the registry, with their headline benchmark lift.